Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming Paper • 2606.31227 • Published 29 days ago • 14
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair Paper • 2606.26978 • Published Jun 25 • 4
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders Paper • 2605.27354 • Published May 26 • 15
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning Paper • 2605.14212 • Published May 14 • 19